Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for automatically detecting unsafe behaviors of workers based on machine vision

A security behavior and automatic detection technology, applied in the field of security detection and security monitoring, to achieve the effects of less time delay, improved accuracy and reduced workload

Pending Publication Date: 2021-04-06
SOUTHWEST PETROLEUM UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to automatically detect unsafe behaviors of workers and receive the recognition results, thereby reducing the occurrence of worker production accidents

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for automatically detecting unsafe behaviors of workers based on machine vision
  • Method for automatically detecting unsafe behaviors of workers based on machine vision
  • Method for automatically detecting unsafe behaviors of workers based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to make the object, technical solution and features of the present invention more clear, the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0028] Please refer to figure 1 , figure 2 Shown, the present invention a kind of method based on machine vision automatic detection worker's unsafe behavior, comprises the steps:

[0029] Step S10: Obtain a large number of raw images of unsafe behaviors of workers.

[0030] Step S20: Mark the category and location of the unsafe behavior on each image to create an unsafe behavior label image.

[0031] Step S30: Build a target detection model, divide the label images into a training set and a verification set, use the label images to train and verify the target detection model, and compare the predicted labels with the actual labels to judge the classification ability of the model to test Whether the classification ability of the model can meet the requirement...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for automatically detecting unsafe behaviors of workers based on machine vision. The method comprises the steps that S10, acquiring original images of the unsafe behaviors of workers; S20, manufacturing label images of the unsafe behaviors; S30, constructing a target detection model, and then training and verifying the model; and S40, obtaining a real-time monitoring video, inputting the obtained image frame into the target detection model for detection, automatically identifying unsafe behaviors of workers, and receiving an identification result through monitoring software. According to the method for automatically identifying the unsafe behaviors of the workers, the principle is that the unsafe behavior database of the workers is established, the unsafe actions of the workers are automatically identified through a deep learning algorithm, results are displayed, and therefore the occurrence rate of the unsafe behaviors of the workers is reduced. Compared with a traditional monitoring method, the method has the advantages of being automatic, good in monitoring effect, easy to operate and the like.

Description

technical field [0001] The invention relates to the technical fields of safety monitoring and safety detection, in particular to a method for automatically detecting workers' unsafe behaviors based on machine vision. Background technique [0002] In recent years, the development of my country's construction industry has advanced by leaps and bounds. Due to the harsh geological environment and complex construction techniques of engineering projects, accidents such as falling from heights, object strikes, vehicle injuries, collapses, collisions, and electric shocks have caused frequent casualties during the construction process. . Through the statistics of construction safety production accidents and their causes in recent years, it is found that workers' unsafe behavior is an important factor leading to accidents, so it is imminent to strengthen the monitoring and management of workers' unsafe behavior. [0003] However, the traditional monitoring method is to record workers'...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/52G06V2201/07G06N3/045G06F18/214
Inventor 胡启军敖琪何乐平
Owner SOUTHWEST PETROLEUM UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com